© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168043
    Prev
    Next
    INDEX
    Explanations

    dictionary key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    塗
    0.33
    รง
    0.33
     लक्ष्मीबाई
    0.32
     участи
    0.32
    कांना
    0.32
     expresar
    0.32
    spars
    0.31
     अटे
    0.31
    ший
    0.31
     оки
    0.31
    POSITIVE LOGITS
    тен
    0.38
     Pathology
    0.38
    omás
    0.38
    சிவ
    0.35
    '$.
    0.35
    
    0.34
     பள்ளத்தா
    0.34
     Spin
    0.33
    დება
    0.33
    Sit
    0.32
    Activations Density 0.011%

    No Known Activations